Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1672 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.3545. Min Act: -0.0001
Data Index: 85421 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.2667. Min Act: -0.0001
Data Index: 925010 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.2084. Min Act: -0.0000
Data Index: 732602 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1652. Min Act: -0.0001
Data Index: 336515 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1531. Min Act: -0.0001
Data Index: 440896 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1509. Min Act: -0.0001
Data Index: 660285 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1474. Min Act: -0.0001
Data Index: 336906 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1502. Min Act: -0.0001
Data Index: 817688 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1517. Min Act: -0.0001
Data Index: 1067497 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1442. Min Act: -0.0001
Data Index: 1318587 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1479. Min Act: -0.0001
Data Index: 1073352 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1433. Min Act: -0.0001
Data Index: 263553 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1469. Min Act: -0.0001
Data Index: 791923 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1387. Min Act: -0.0001
Data Index: 70387 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1431. Min Act: -0.0001
Data Index: 425720 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1404. Min Act: -0.0001
Data Index: 530177 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1287. Min Act: -0.0001
Data Index: 548753 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1281. Min Act: -0.0001
Data Index: 1182305 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1357. Min Act: -0.0001
Data Index: 555728 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3545. Min Range: -0.3545
Max Act: 0.1418. Min Act: -0.0001
Data Index: 938567 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19